메뉴
Agents should invoke this skill when defects, regressions, failed tests, unexpected behavior, or spec mismatches are found. Produces structured reproducible bug reports with severity, evidence, environment, and actionable next steps.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Creates polished self-contained HTML explanation reports for complex, multi-step topics using overview tables, evidence cards, adaptive graphs or diagrams, meaningful SVG/media, and accessible tabs for long pages. Use when the user requests a browser-readable diagnostic report, technical guide, decision analysis, implementation plan, investigation, or research synthesis as HTML.
Agents should invoke this skill to create, migrate, inspect, apply, verify, or roll back versioned PATCH.md v2 lifecycle packages with machine-readable manifests, deterministic plans, drift detection, and transactional safety.
Safely inspect, search, render, edit, diff, validate, and commit Microsoft Word DOCX files with the dedicated docx_* tools. Use for DOCX/DOTX/DOCM/DOTM document work; enforces dry-run-first edits, active-content refusal, preservation checks, and save-as by default.
Agents should invoke this skill for high-stakes or complex research needing multi-source evidence, scientific/technical fact-checking, decision traces, or rigorous verification. Runs deterministic two-phase research with schema/policy validation.
Use when inspecting, reading, rendering, editing, formatting, diffing, or validating local .xlsx and .xlsm Excel workbooks. Provides fail-closed workbook tools with dry-run planning, SHA-256 conflict protection, PNG previews, and byte-identity checks for VBA and other protected OOXML parts. Do not use for CSV-only work or for executing/editing VBA.
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
| name | bug-reporter |
| description | Agents should invoke this skill when defects, regressions, failed tests, unexpected behavior, or spec mismatches are found. Produces structured reproducible bug reports with severity, evidence, environment, and actionable next steps. |
Produce clear, actionable, reproducible bug reports.
Every bug report follows this exact structure:
## BUG-<number>: <Short descriptive title>
**Severity:** Blocker / Critical / Major / Minor
**Module:** <module name from architecture>
**Spec Reference:** <requirement ID or spec section>
**Found During:** <test case ID or manual testing description>
### Reproduction Steps
**Preconditions:**
- [Required state, configuration, or setup]
**Steps:**
1. [Exact step]
2. [Exact step]
3. [Exact step — this triggers the bug]
### Expected Result
[What the spec says should happen, with spec section reference]
### Actual Result
[What actually happens]
**Evidence:**
- Error message: `<exact error text>`
- Log output: `<relevant log lines>`
- Test output: `<test failure details>`
### Environment
- OS: [if relevant]
- Runtime: [Node version, Rust toolchain, Python version]
- Configuration: [relevant config settings]
- Database state: [if relevant]
### Analysis
**Likely root cause:** [Brief assessment if obvious, "Unknown" if not]
**Related bugs:** [BUG-XXX if related]
**Workaround:** [If one exists, describe it. Otherwise "None known."]
Within a QA pass, bugs are numbered sequentially: BUG-001, BUG-002, etc. If re-testing after fixes, new bugs continue the sequence (BUG-005, BUG-006). Fixed bugs keep their original number — mark them as FIXED in the report.
At the top of every QA report, include a summary:
| Bug | Severity | Module | Status | Summary |
|---|---|---|---|---|
| BUG-001 | Critical | auth | OPEN | Login fails with valid credentials |
| BUG-002 | Major | profile | OPEN | Avatar upload accepts files > 10MB |
| BUG-003 | Minor | ui | OPEN | Footer overlaps on mobile viewport |
When Forge fixes a bug:
Watchdog skill — Structured bug reporting and severity classification